A Feature Compensation Approach Using High-Order Vector Taylor Series Approximation of an Explicit Distortion Model for Noisy Speech Recognition

被引：0
|
作者：
Du, Jun [1 ]
Huo, Qiang [1 ]
机构：
[1] Microsoft Res Asia, Beijing, Peoples R China
来源：
INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5 | 2008年
关键词：
robust speech recognition; feature compensation; vector Taylor series; distortion model;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents a new feature compensation approach to noisy speech recognition by using high-order vector Taylor series (HOVTS) approximation of an explicit model of environmental distortions. Formulations for maximum likelihood (ML) estimation of noise model parameters and minimum mean-squared error (MMSE) estimation of clean speech are derived. Experimental results on Aurora2 database demonstrate that the proposed approach achieves consistently significant improvement in recognition accuracy compared to traditional first-order VTS based feature compensation approach.
引用
收藏
页码：1257 / 1260
页数：4
相关论文
共 50 条
  • [1] A Feature Compensation Approach Using High-Order Vector Taylor Series Approximation of an Explicit Distortion Model for Noisy Speech Recognition
    Du, Jun
    Huo, Qiang
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2011, 19 (08): : 2285 - 2293
  • [2] A feature compensation approach using piecewise linear approximation of an explicit distortion model for noisy speech recognition
    Du, Jun
    Huo, Qiang
    2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4721 - +
  • [3] EVALUATION OF A FEATURE COMPENSATION APPROACH USING HIGH-ORDER VECTOR TAYLOR SERIES APPROXIMATION OF AN EXPLICIT DISTORTION MODEL ON AURORA2, AURORA3, AND AURORA4 TASKS
    Du, Jun
    Huo, Qiang
    Hu, Yu
    2008 6TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2008, : 81 - 84
  • [4] Speech recognition in noisy environments using first-order vector Taylor series
    Kim, DY
    Un, CK
    Kim, NS
    SPEECH COMMUNICATION, 1998, 24 (01) : 39 - 49
  • [5] A VTS-BASED FEATURE COMPENSATION APPROACH TO NOISY SPEECH RECOGNITION USING MIXTURE MODELS OF DISTORTION
    Du, Jun
    Huo, Qiang
    2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7078 - 7082
  • [6] Overcoming the vector taylor series approximation in speech feature enhancement -: A particle filter approach
    Faubel, Friedrich
    Woelfel, Matthias
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 557 - +
  • [7] Feature compensation algorithm based on vector Taylor series for speaker recognition
    Wu, Haiyang
    Yang, Feiran
    Zhou, Lin
    Wu, Zhenyang
    Shengxue Xuebao/Acta Acustica, 2013, 38 (01): : 105 - 112
  • [8] An Improved VTS Feature Compensation using Mixture Models of Distortion and IVN Training for Noisy Speech Recognition
    Du, Jun
    Huo, Qiang
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2014, 22 (11) : 1601 - 1611
  • [9] AN ANALYSIS OF VECTOR TAYLOR SERIES MODEL COMPENSATION FOR NON-STATIONARY NOISE IN SPEECH RECOGNITION
    Duc Hoang Ha Nguyen
    Xiao, Xiong
    Chng, Eng Siong
    Li, Haizhou
    2012 8TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING, 2012, : 131 - 135
  • [10] Using vector Taylor series with noise clustering for speech recognition in non-stationary noisy environments
    Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
    High Technol Letters, 2006, 1 (18-23):
12345